DeepAI AI Chat
Log In Sign Up

Physical Primitive Decomposition

by   Zhijian Liu, et al.

Objects are made of parts, each with distinct geometry, physics, functionality, and affordances. Developing such a distributed, physical, interpretable representation of objects will facilitate intelligent agents to better explore and interact with the world. In this paper, we study physical primitive decomposition---understanding an object through its components, each with physical and geometric attributes. As annotated data for object parts and physics are rare, we propose a novel formulation that learns physical primitives by explaining both an object's appearance and its behaviors in physical events. Our model performs well on block towers and tools in both synthetic and real scenarios; we also demonstrate that visual and physical observations often provide complementary signals. We further present ablation and behavioral studies to better understand our model and contrast it with human performance.


page 4

page 8

page 12


Hierarchical Relational Inference

Common-sense physical reasoning in the real world requires learning abou...

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning

Object-based factorizations provide a useful level of abstraction for in...

ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking

Physical intuition is pivotal for intelligent agents to perform complex ...

DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions

We study the problem of learning physical object representations for rob...

Unsupervised Discovery of 3D Physical Objects from Video

We study the problem of unsupervised physical object discovery. Unlike e...

ESPRIT: Explaining Solutions to Physical Reasoning Tasks

Neural networks lack the ability to reason about qualitative physics and...

Curiosity-driven Intuitive Physics Learning

Biological infants are naturally curious and try to comprehend their phy...